© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 23810
    Prev
    Next
    INDEX
    Explanations

    mentions of conflicts and geopolitical events, particularly related to Syria

    oai_token-act-pair · gpt-3.5-turbo

    definite articles followed by phrases indicating news reports or updates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĦ
    -0.81
    Reviewed
    -0.80
    acea
    -0.80
    roo
    -0.78
    biz
    -0.77
    leen
    -0.76
    ago
    -0.75
    Tax
    -0.75
    Beta
    -0.75
    Chain
    -0.74
    POSITIVE LOGITS
     ceasefire
    1.35
     truce
    1.32
     insurgency
    1.31
     rebels
    1.30
     militants
    1.27
     uprising
    1.23
     insurgents
    1.22
     jihadists
    1.18
     army
    1.18
     militias
    1.18
    Activations Density 0.222%

    No Known Activations